Staff Research Engineer Interactive Avatars
Synthesia is an active London-based enterprise AI video platform that lets businesses create, localize, manage, and publish videos using AI avatars and voiceovers.
Funding history
About Synthesia
Synthesia Limited provides browser-based AI video creation for business communications, training, sales enablement, marketing, and support. Its platform includes AI-assisted creation, avatars, voiceovers, translation/localization, collaboration, and publishing workflows.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will develop interactive avatar video diffusion models and turn research into product capabilities. You will add conditioning signals, build real-time streaming methods, improve perceptual reactions and visual quality, create evaluation systems, and define data needs with the data team.
Requirements
- Machine learning and computer vision background
- Industry experience with diffusion models
- PyTorch proficiency
- Python engineering skills
- Git and version control knowledge
- Experience communicating hypotheses, experiments, and results
Responsibilities
- Adapt diffusion models for audio, motion, and interaction conditioning
- Develop real-time streaming methods for long video sequences
- Build perceptual capabilities for user-audio understanding and contextual reactions
- Improve lip-sync accuracy, motion realism, and visual quality
- Build evaluation frameworks and test suites
- Define data needs and support high-quality datasets
- Track research in world models, interactive agents, and diffusion models
Benefits
- Stock options
- Bonus
- Hybrid work or remote work in Europe
- 25 days of annual leave plus public holidays
- Regular planning and social events at hubs